INDEX
Explanations
references to government structures and legal principles
New Auto-Interp
Negative Logits
Society
-0.15
chet
-0.14
DISCLAIM
-0.14
SES
-0.14
vale
-0.13
luv
-0.13
_DECLARE
-0.13
diss
-0.13
outu
-0.13
aja
-0.13
POSITIVE LOGITS
federal
0.35
local
0.32
Local
0.32
-local
0.31
local
0.31
_local
0.31
Local
0.30
decentral
0.30
/local
0.29
decentralized
0.28
Activations Density 0.159%